upload models & model_index.json

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+shape_predictor_68_face_landmarks.dat filter=lfs diff=lfs merge=lfs -text

diffswap.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf7df1f6ebdc9d67ec0c46a066fea59b91386dde465c2e897a12ebbed8d017ea
+size 3498619659

glint360k_r100.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f631718e783448b41631e15073bdc622eaeef56509bbad4e5085f23bd32db83
+size 261223796

model_index.json

@@ -0,0 +1,87 @@
+{
+    "model": {
+        "base_learning_rate": 5e-07,
+        "target": "ldm.models.diffusion.ddpm.LatentDiffusion",
+        "params": {
+            "ckpt_path": null,
+            "linear_start": 0.0015,
+            "linear_end": 0.0195,
+            "num_timesteps_cond": 1,
+            "log_every_t": 200,
+            "timesteps": 1000,
+            "first_stage_key": "image",
+            "image_size": 64,
+            "channels": 3,
+            "cond_stage_trainable": true,
+            "cond_stage_key": "faceattr",
+            "conditioning_key": "crossattn",
+            "monitor": "val/loss_simple_ema",
+            "unet_config": {
+                "target": "ldm.modules.diffusionmodules.openaimodel.UNetModel",
+                "params": {
+                    "image_size": 64,
+                    "in_channels": 3,
+                    "out_channels": 3,
+                    "model_channels": 224,
+                    "attention_resolutions": [
+                        8,
+                        4,
+                        2
+                    ],
+                    "num_res_blocks": 2,
+                    "channel_mult": [
+                        1,
+                        2,
+                        3,
+                        4
+                    ],
+                    "num_head_channels": 32,
+                    "use_spatial_transformer": true,
+                    "transformer_depth": 1,
+                    "context_dim": 256
+                }
+            },
+            "first_stage_config": {
+                "target": "ldm.models.autoencoder.VQModelInterface",
+                "params": {
+                    "embed_dim": 3,
+                    "n_embed": 8192,
+                    "ddconfig": {
+                        "double_z": false,
+                        "z_channels": 3,
+                        "resolution": 256,
+                        "in_channels": 3,
+                        "out_ch": 3,
+                        "ch": 128,
+                        "ch_mult": [
+                            1,
+                            2,
+                            4
+                        ],
+                        "num_res_blocks": 2,
+                        "attn_resolutions": [],
+                        "dropout": 0.0
+                    },
+                    "lossconfig": {
+                        "target": "torch.nn.Identity"
+                    }
+                }
+            },
+            "cond_stage_config": {
+                "target": "ldm.modules.encoders.modules.FaceEmbedder",
+                "params": {
+                    "lmk_dim": 256,
+                    "comb_mode": "stack",
+                    "keys": [
+                        "image",
+                        "landmark"
+                    ],
+                    "attention": true,
+                    "merge_eyes": true,
+                    "face_model": "r100",
+                    "affine_crop": true
+                }
+            }
+        }
+    }
+}

shape_predictor_68_face_landmarks.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbdc2cb80eb9aa7a758672cbfdda32ba6300efe9b6e6c7a299ff7e736b11b92f
+size 99693937